{"id":"https://openalex.org/W4413917766","doi":"https://doi.org/10.1109/icra55743.2025.11128430","title":"Fine-Grained Open-Vocabulary Object Detection with Fined-Grained Prompts: Task, Dataset and Benchmark","display_name":"Fine-Grained Open-Vocabulary Object Detection with Fined-Grained Prompts: Task, Dataset and Benchmark","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917766","doi":"https://doi.org/10.1109/icra55743.2025.11128430"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.14862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100414211","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-3667-6323"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Department of Software Engineering, Northeastern University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yijing Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijing Hua","raw_affiliation_strings":["Department of Software Engineering, Northeastern University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108824574","display_name":"Haojiang Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojiang Chai","raw_affiliation_strings":["Department of Software Engineering, Northeastern University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695201","display_name":"Yanbo Wang","orcid":"https://orcid.org/0000-0003-3428-4585"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbo Wang","raw_affiliation_strings":["Department of Software Engineering, Northeastern University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062814209","display_name":"TengQi Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"TengQi Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4143,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82156062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13860","last_page":"13867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9337000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120040893554688},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7987641096115112},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6632289886474609},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6599735617637634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4589274227619171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3432950973510742},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0523131787776947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120040893554688},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7987641096115112},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6632289886474609},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6599735617637634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4589274227619171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3432950973510742},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0523131787776947},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra55743.2025.11128430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.14862","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.14862","pdf_url":"https://arxiv.org/pdf/2503.14862","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.14862","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.14862","pdf_url":"https://arxiv.org/pdf/2503.14862","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413917766.pdf","grobid_xml":"https://content.openalex.org/works/W4413917766.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2064985253","https://openalex.org/W2533598788","https://openalex.org/W2797977484","https://openalex.org/W2948672349","https://openalex.org/W2984121207","https://openalex.org/W3092663126","https://openalex.org/W3108849448","https://openalex.org/W3172112830","https://openalex.org/W3173859428","https://openalex.org/W3206277407","https://openalex.org/W3213192039","https://openalex.org/W4213450898","https://openalex.org/W4290065491","https://openalex.org/W4312424618","https://openalex.org/W4313447176","https://openalex.org/W4386076683","https://openalex.org/W4390873750","https://openalex.org/W4391547487","https://openalex.org/W4395080758","https://openalex.org/W4402727832","https://openalex.org/W4404612908"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Open-vocabulary":[0],"detectors":[1,68,155],"are":[2,176],"proposed":[3],"to":[4,25,35,48,94,114,121,128],"locate":[5],"and":[6,27,46,55,102,111,148,174],"recognize":[7],"objects":[8],"in":[9,14,117,119],"novel":[10,86],"classes.":[11],"However,":[12],"variations":[13],"vision-aware":[15],"language":[16],"vocabulary":[17],"data":[18],"used":[19],"for":[20,145,159],"open-vocabulary":[21,96,149],"learning":[22],"can":[23,69],"lead":[24],"unfair":[26],"unreliable":[28],"evaluations.":[29],"Recent":[30],"evaluation":[31],"methods":[32],"have":[33,138],"attempted":[34],"address":[36],"this":[37],"issue":[38],"by":[39],"incorporating":[40],"object":[41,92,134,154],"properties":[42,54],"or":[43],"adding":[44],"locations":[45,56],"characteristics":[47],"the":[49,59,63,95,129],"captions.":[50],"Nevertheless,":[51],"since":[52],"these":[53],"depend":[57],"on":[58,156],"specific":[60],"details":[61,116],"of":[62,66,108,131],"images":[64,118],"instead":[65],"classes,":[67],"not":[70],"make":[71],"accurate":[72],"predictions":[73],"without":[74],"precise":[75],"descriptions":[76],"provided":[77],"through":[78],"human":[79],"annotation.":[80],"This":[81],"paper":[82],"introduces":[83],"3F-OVD,":[84],"a":[85,105,140,165],"task":[87,99],"that":[88],"extends":[89],"supervised":[90,147],"fine-grained":[91,133],"detection":[93,135],"setting.":[97],"Our":[98,171],"is":[100],"intuitive":[101],"challenging,":[103],"requiring":[104],"deep":[106],"understanding":[107],"Fine-grained":[109,115,124],"captions":[110],"careful":[112],"attention":[113],"order":[120],"accurately":[122],"detect":[123],"objects.":[125],"Additionally,":[126],"due":[127],"scarcity":[130],"qualified":[132],"datasets,":[136],"we":[137,163],"created":[139],"new":[141],"dataset,":[142],"NEU-171K,":[143],"tailored":[144],"both":[146,160],"settings.":[150,161],"We":[151],"benchmark":[152],"state-of-the-art":[153],"our":[157],"dataset":[158],"Furthermore,":[162],"propose":[164],"simple":[166],"yet":[167],"effective":[168],"post-processing":[169],"technique.":[170],"data,":[172],"annotations":[173],"codes":[175],"available":[177],"at":[178],"https://github.com/tengerye/3FOVD.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}